Anfis Applied to a Ship Autopilot Design

Abstract

Using a batch learning scheme and a hybrid learning rule, i.e. BP algorithm is applied to the learning of premise parameters, while least square algorithm to the learning of consequent parameters, an ANFIS system for ship autopilot with two inputs and one output, three fuzzy zones, nine fuzzy rules is trained. Training data come from a PD course control system, then the trained ANFIS autopilot controls an oil tanker that is described by a nonlinear ship model. The simulating results by Matlab indicate that the performance of ANFIS controller is similar to that of the training PD controller with good robustness.